{"total":86,"rows":[{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2104.02138","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","created":"2021-04-05","cited_by_count":42,"area":null},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37,"area":null},{"id":"2412.06299","title":"4D Gaussian Splatting with Scale-aware Residual Field and Adaptive Optimization for Real-time Rendering of Temporally Complex Dynamic Scenes","created":"2024-12-09","cited_by_count":37,"area":null},{"id":"2106.02182","title":"Self-supervised Dialogue Learning for Spoken Conversational Question Answering","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2102.06283","title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","created":"2021-02-11","cited_by_count":27,"area":null},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","cited_by_count":22,"area":null},{"id":"2102.00804","title":"Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript","created":"2021-02-01","cited_by_count":21,"area":null},{"id":"2305.13512","title":"Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding","created":"2023-05-22","cited_by_count":21,"area":null},{"id":"2203.00006","title":"Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems","created":"2022-02-26","cited_by_count":20,"area":null},{"id":"2211.05869","title":"A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","created":"2022-11-10","cited_by_count":18,"area":null},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","cited_by_count":18,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2102.07370","title":"Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"area":null},{"id":"2106.13045","title":"Where are we in semantic concept extraction for Spoken Language Understanding?","created":"2021-06-24","cited_by_count":11,"area":null},{"id":"2204.00803","title":"End-to-end model for named entity recognition from speech without paired training data","created":"2022-04-02","cited_by_count":11,"area":null},{"id":"2102.01013","title":"End2End Acoustic to Semantic Transduction","created":"2021-02-01","cited_by_count":10,"area":null},{"id":"2210.08759","title":"Towards Relation Extraction From Speech","created":"2022-10-17","cited_by_count":10,"area":null},{"id":"2102.06750","title":"Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2108.08405","title":"Integrating Dialog History into End-to-End Spoken Language Understanding Systems","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2108.13048","title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2104.05752","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2105.07071","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2111.00400","title":"FANS: Fusing ASR and NLU for on-device SLU","created":"2021-10-31","cited_by_count":8,"area":null},{"id":"2204.01893","title":"Deliberation Model for On-Device Spoken Language Understanding","created":"2022-04-04","cited_by_count":8,"area":null},{"id":"2104.03842","title":"RNN Transducer Models For Spoken Language Understanding","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2106.04660","title":"Sequential End-to-End Intent and Slot Label Classification and Localization","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2210.05291","title":"On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2104.10357","title":"Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning","created":"2021-04-21","cited_by_count":6,"area":null},{"id":"2105.04719","title":"Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2206.14318","title":"Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2207.01893","title":"ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks","created":"2022-07-05","cited_by_count":6,"area":null},{"id":"2210.16554","title":"End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator","created":"2022-10-29","cited_by_count":6,"area":null},{"id":"2305.18096","title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2401.11382","title":"Using Large Language Model for End-to-End Chinese ASR and NER","created":"2024-01-21","cited_by_count":6,"area":null},{"id":"2106.15238","title":"Representation based meta-learning for few-shot spoken intent recognition","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2109.02823","title":"Learning Visual-Audio Representations for Voice-Controlled Robots","created":"2021-09-07","cited_by_count":5,"area":null},{"id":"2304.11073","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2104.01287","title":"Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems","created":"2021-04-03","cited_by_count":4,"area":null},{"id":"2205.12818","title":"On Building Spoken Language Understanding Systems for Low Resourced Languages","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2401.14625","title":"Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline","created":"2024-01-26","cited_by_count":4,"area":null},{"id":"2204.03315","title":"Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2207.00352","title":"Toward Low-Cost End-to-End Spoken Language Understanding","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2207.08179","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2211.13703","title":"Multitask Learning for Low Resource Spoken Language Understanding","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2305.17499","title":"CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2306.06819","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2401.15385","title":"Towards Event Extraction from Speech with Contextual Clues","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2408.07277","title":"Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2103.16674","title":"Pre-training for low resource speech-to-intent applications","created":"2021-03-30","cited_by_count":2,"area":null},{"id":"2210.12857","title":"Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings","created":"2022-10-23","cited_by_count":2,"area":null},{"id":"2211.07710","title":"End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2212.08489","title":"Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2307.01323","title":"Semantic enrichment towards efficient speech representations","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2307.12134","title":"Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2408.06043","title":"Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2601.05911","title":"Pantagruel: Unified Self-Supervised Encoders for French Text and Speech","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2107.01571","title":"Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model","created":"2021-07-04","cited_by_count":1,"area":null},{"id":"2311.04923","title":"Is one brick enough to break the wall of spoken dialogue state tracking?","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2312.01842","title":"Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2406.12141","title":"A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2407.07425","title":"Out-of-distribution generalisation in spoken language understanding","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2606.24910","title":"End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2106.08637","title":"Topic Classification on Spoken Documents Using Deep Acoustic and Linguistic Features","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2203.12067","title":"Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2204.03879","title":"A Study of Different Ways to Use The Conformer Model For Spoken Language Understanding","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2207.00349","title":"Vers la compr\\'ehension automatique de la parole bout-en-bout \\`a moindre effort","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2302.10186","title":"E2E Spoken Entity Extraction for Virtual Agents","created":"2023-02-16","cited_by_count":0,"area":null},{"id":"2303.06585","title":"Improving the Intent Classification accuracy in Noisy Environment","created":"2023-03-12","cited_by_count":0,"area":null},{"id":"2305.02937","title":"End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2307.01310","title":"Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition Systems","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2309.02780","title":"GRASS: Unified Generation Model for Speech-to-Semantic Tasks","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2311.04922","title":"Are cascade dialogue state tracking models speaking out of turn in spoken dialogues?","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2403.15510","title":"Privacy-Preserving End-to-End Spoken Language Understanding","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2405.15097","title":"Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2505.20176","title":"\"KAN you hear me?\" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2511.07493","title":"Enabling Automatic Self-Talk Detection via Earables","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2603.16483","title":"On the Emotion Understanding of Synthesized Speech","created":"2026-03-17","cited_by_count":0,"area":null}],"next_cursor":null}